def test_dame_gender_dataset2genderlist_method_returns_correct_result(
self):
g = Gender()
gl = g.dataset2genderlist(dataset="files/names/all.csv")
self.assertEqual(gl[0:4], [1, 1, 1, 1])
gl2 = g.dataset2genderlist(dataset="files/names/yob2017.txt")
self.assertEqual(gl2[0:4], [0, 0, 0, 0])
elif (args.categorical == "noletters"):
g.features_list2csv(categorical="noletters",
path="files/names/allnoundefined.csv")
features = "files/features_list_cat.csv"
elif (args.categorical == "nocategorical"):
g.features_list2csv(categorical="nocategorical",
path="files/names/allnoundefined.csv")
features = "files/features_list_no_cat.csv"
else:
g.features_list2csv(categorical="both", path="files/names/all.csv")
features = "files/features_list.csv"
## STEP1: N COMPONENTS + 1 TARGET
x = pd.read_csv(features)
#print(x.columns)
y = g.dataset2genderlist(dataset="files/names/allnoundefined.csv")
#print(y)
# STEP2: ADDING TARGET
target = pd.DataFrame(data=y, columns=['target component'])
finalDf = x.join(target)
# STEP3: NORMALIZE DATA
from sklearn import preprocessing
data_scaled = pd.DataFrame(preprocessing.scale(finalDf),
columns=finalDf.columns)
# STEP4: PCA
pca = PCA(n_components=int(args.components))
pca.fit_transform(data_scaled)